recall_decisions
AI agents call recall_decisions to retrieve information from Metis Public Health without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'recall' indicates data retrieval rather than modification, creation, or destruction. In the context of a personal research/knowledge management system (Metis), recalling decisions would fetch previously stored decision records. No side effects, destructive operations, or external execution are implied.
From the tool's definition Tool name 'recall_decisions' and context from sibling tools (add_memory_entry, add_journal_entry, aggregate_reflexions) suggest this retrieves or queries stored decision data. The description is empty, which reduces confidence.
Attacks that exploit this kind of access
recall_decisions. It is categorised as a Read tool in the Metis Public Health MCP Server, which means it retrieves data without modifying state.
Register the Metis Public Health MCP server in PolicyLayer and add a rule for recall_decisions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Metis Public Health. Nothing to install.
recall_decisions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the recall_decisions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for recall_decisions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
recall_decisions is provided by the Metis Public Health MCP server (sveritg/metis_ph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →